jd-opensource

jd-opensource

JD.com 京东开源官方账号

公告

README

JD Open Source - Open Technology, Shared Future.

中文

Our Mission

We are dedicated to empowering developers and enterprises through open technology, collectively building an efficient, reliable, and innovative tech ecosystem. We believe that open source is a bridge connecting technology with the community, accelerating technological accessibility and value creation.

Our Governance

Our open-source projects operate under a transparent governance model, ensuring their healthy and sustainable growth. We are guided by:

  • Open Decision-Making: All major technical decisions are openly discussed within the community. We welcome feedback and suggestions from everyone.
  • Meritocracy: Roles and permissions are based on an individual's contributions to the project. Anyone who consistently contributes has the opportunity to become a core maintainer.
  • Code of Conduct: We strictly adhere to our Code of Conduct to ensure a friendly, inclusive, and respectful community for all.

How to Get Involved

We welcome everyone with a passion for technology to join our community, whether you are a seasoned developer or just starting out. Here are a few ways you can contribute:

  • Submit an Issue: Found a bug or have a new feature idea? Feel free to open an issue in our project repositories.
  • Contribute Code: Submit your code fixes or new features via a Pull Request. Please read the project's contribution guide first.
  • Improve Documentation: Help us translate or improve our documentation to benefit more users.
  • Join the Discussion: Participate in our community forums or chat groups to share your thoughts and experiences.

Our Projects

You can find all our open-source projects here https://gitcode.com/jd-x-opensource, or visit our homepage for more information.

Contact Us

org.ospo1@jd.com

热门项目
35

JoyAI-Echo,这是一个独立的、仅用于推理的版本,旨在实现分钟级多镜头音视频生成。它采用了经过蒸馏的DMD生成器、配对的跨模态记忆以及故事级别的一致性。其性能的核心在于,一个跨模态视听记忆库能够在长达五分钟的视频中保持角色外观和语音音色的一致性。同时,一个训练后处理流程将基于记忆的强化学习与分布匹配蒸馏相结合,实现了7.5倍的速度提升,显著增强了视觉质量和对齐效果。

1

JoyAI-Echo: Pushing the Frontier of Long Audio-Visual Generation

  • JoyAI-Echo,这是一个独立的、仅用于推理的版本,旨在实现分钟级多镜头音视频生成。它采用了经过蒸馏的DMD生成器、配对的跨模态记忆以及故事级别的一致性。其性能的核心在于,一个跨模态视听记忆库能够在长达五分钟的视频中保持角色外观和语音音色的一致性。同时,一个训练后处理流程将基于记忆的强化学习与分布匹配蒸馏相结合,实现了7.5倍的速度提升,显著增强了视觉质量和对齐效果。

    35
    0
    更新于 2 天前
    Like
  • JoyAI-Echo: Pushing the Frontier of Long Audio-Visual Generation

    Python
    1
    0
    NOASSERTION
    更新于 4 天前
    Star
  • 暂无简介

    Python
    0
    0
    更新于 26 天前
    Like
  • 暂无简介

    Jinja
    0
    0
    更新于 12 天前
    Like
  • 暂无简介

    Jinja
    0
    0
    更新于 12 天前
    Like
  • 暂无简介

    Python
    0
    0
    更新于 25 天前
    Like
  • 暂无简介

    Python
    0
    0
    更新于 25 天前
    Like
  • 暂无简介

    0
    0
    更新于 25 天前
    Like
  • 暂无简介

    Python
    0
    0
    更新于 25 天前
    Like
  • 暂无简介

    Jinja
    0
    0
    更新于 26 天前
    Like
查看全部项目 >
公告
成就
37
Star
0
Fork
176
Download
常用语言
Python
Jinja
社区动态